Exploring the effects of feeding emotional stimuli to large language models

Regarding your last comment, I think it rings true, and further, politics (or at least political communication) is to a degree citizen prompt engineering.

It further strikes me that, if these are true:

(1) Influencing large groups of people is at least somewhat equivalent to prompt engineering. (2) Large language models reflect at least some degree of similarity with how humans respond to the same prompts.

Then you could use LLMs to test the influence of different psychological manipulations before using them on large groups of people.

Try different prompts, see which one gets the best response from an LLM, then use it on people.